INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 unknownFields

-0.89

 >=",

-0.68

 saites

-0.67

gestone

-0.62

 contextLoads

-0.61

COUVER

-0.61

 erfol

-0.59

lihood

-0.59

 препратки

-0.59

laken

-0.58

POSITIVE LOGITS

########.

0.76

 GenerationType

0.68

mybatisplus

0.56

 MonoBehaviour

0.52

 retractable

0.50

Personendaten

0.49

 existed

0.48

dispose

0.47

 interviewed

0.46

apimachinery

0.45

Activations Density 0.026%

No Comments

No Known Activations